Google has introduced the Gemini Decisions API, powered by a new Gemini Decision 1 model, available through the Gemini API in Google AI Studio. According to the November 11 announcement, the API is designed for bounded decision tasks such as tool selection, policy checks, model routing and context grading.
The system evaluates up to 1,000 independent yes/no, multiple-choice and rubric-scoring questions against a single multimodal input in one forward pass, supporting text, images, audio, video and PDFs up to 256,000 tokens. Instead of generating answer text token by token, Gemini Decision 1 scores candidate options directly, returning probabilities and confidence scores.
Google reports 150-250 ms end-to-end latency and median model compute time of 50-100 ms across multimodal inputs and contexts up to 16,000 tokens, remaining nearly flat from 1 to 100 questions per request. Pricing is $0.10 per million input tokens with zero output tokens billed. The company claims the service is nearly 5x cheaper than Gemini 3.5 Flash-Lite with the Interactions API across a shared benchmark suite.
On benchmarks spanning agent routing, reasoning, ranking and multimodal understanding, Google says Gemini Decision 1 leads across the suite with the lowest calibration error, though specific benchmark names and scores were not detailed. Users can combine modalities in one shared input, such as pairing a call recording with account metadata or a scanned PDF claim with damage photos, and can tune resolution on image and video inputs to control visual detail and token cost.